The flickering streetlights cast long, dancing shadows that seemed to mock him as he walked. He kept glancing over his shoulder, a nervous tic. The cafe, bathed in a warm inviting glow, was where he’d seen her. Sarah. Or at least, the woman who looked exactly like Sarah, his childhood confidante. He'd tried to approach her, but her blank stare and confused "I don't think we've met" had sent a chill down his spine. Now, every rustle of leaves, every car door slamming, felt like a threat.

His reflection in the shop windows seemed to leer back at him, a stranger. Had she been lying? Why would she? He clenched his jaw, the muscles tightening. The air felt thick, heavy, as though someone was watching. He needed to get home. He quickened his pace, the fear clawing at his throat.

Emotion: paranoid

Cluster: Suspicion / Vigilance
PC1 (Valence): -2.37 Negative
PC2 (Disposition): 0.70

Role in Research

This story is one of 1,000 stories generated for the emotion paranoid. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 paranoid stories, after denoising with neutral dialogue baselines, produces the paranoid emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the paranoid vector is projected through the unembedding matrix.

Promoted:
even0.418
마다0.378
paranoid0.371
afraid0.366
🕵0.360
Suppressed:
la-0.628
de-0.541
L-0.472
H-0.470
B-0.434